Copy move and splicing forgery detection using deep convolution neural network, and semantic segmentation
- PDF / 6,675,552 Bytes
- 29 Pages / 439.37 x 666.142 pts Page_size
- 32 Downloads / 235 Views
Copy move and splicing forgery detection using deep convolution neural network, and semantic segmentation Abhishek 1 & Neeru Jindal 1 Received: 20 September 2019 / Revised: 12 June 2020 / Accepted: 2 September 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Image forgeries can be detected and localized by using deep convolution neural network, and semantic segmentation. Color illumination is used to apply color map after preprocessing step. To train VGG-16 with two classes using deep convolution neural network transfer learning approach is used. This algorithm classifies image’s pixels having a forgery or not. These classified images with color pixel label are trained using semantic segmentation to localize forged pixels. These algorithms are tested on GRIP, DVMM, CMFD, and BSDS300 datasets. All these images are divided into two folders. One folder contains all forged images, and another folder contains labels of forged pixels. The experiment result shows that total accuracy is 0.98482, average accuracy is 0.98581, average IoU is 0.91148, weighted IoU is 0.97193, and average boundary F1 score is 0.86404. The forged pixel accuracy is 0.98698, IoU of the forged pixel is 0.83945, and average boundary F1 score of the forged image is 0.79709. Not Forged pixel accuracy is 0.98463, IoU of not forged pixel is 0.98351 and average boundary F1 score of not forged image is 0.93055. The experiment results show that forged pixel and not forged detection accuracy is above 98%, which is best among other methods. Keywords Copy Move Forgery Detection (CMFD) . Splicing Forgery (SF) . Machine Learning (ML) . Deep Learning (DL) . Feature Extraction (FE)
* Neeru Jindal [email protected] Abhishek [email protected]
1
Electronics and Communication Engineering Department, Thapar Institute of Engineering and Technology, Patiala, India
Multimedia Tools and Applications
1 Introduction Currently, digital images are used in print media, digital media, and on the internet. The user-friendly software like Adobe Photoshop, CorelDraw, Paint shop Pro, Filmora, or GIMP change's image content much more comfortably. The content sharing becomes less restrictive and readily achievable by anyone. In today’s scenario, images are widely used as evidence in legal cases. Social media platforms like Facebook, Twitter, Instagram, Telegram, WhatsApp, and YouTube commonly used by everyone and media. Any objectionable images shared by someone on social media platforms are under legal actionable. To verify the genuineness of pictures shared on social media requires an algorithm which tests the reliability of the photograph. The user-friendly image editing software can easily modify images, so the detection and localization of forged copies [9, 34, 36, 37] are becoming an important research topic. Image forgery recognition approaches are of two types active approach and passive approach. The active approach extracts hidden information from the image. The secret information is present in the form of watermarks and dig
Data Loading...
